INDEX

Explanations

prevent

np_max-act · gemini-2.0-flash

mentions of prevention—actions, measures, or policies aimed at stopping harm, disease, failures, or other adverse outcomes.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĤ£ä¸ª

-0.25

 floors

-0.25

 sola

-0.24

_RT

-0.24

gam

-0.24

 mÅ©i

-0.24

ä¸ŃåĽ½å¤§éĻĨ

-0.23

éĢĶå¾Ħ

-0.23

ä¸Ĭåĳ¨

-0.23

 Randall

-0.23

POSITIVE LOGITS

 Morm

0.30

çĤ®

0.27

TURE

0.27

ãĥ¢ãĥİ

0.26

åŀĦæĸŃ

0.26

ä¾¬

0.25

æİ£

0.25

 Perr

0.25

åī¿

0.25

çļĦåĪ°æĿ¥

0.24

Activations Density 0.001%

prevent

mentions of prevention—actions, measures, or policies aimed at stopping harm, disease, failures, or other adverse outcomes.

No Comments

No Known Activations