INDEX

Explanations

article

np_max-act · gemini-2.0-flash

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

know

-0.29

åĪ¸

-0.28

Ð¶Ð¸

-0.28

sez

-0.25

éĥ¯

-0.25

ASON

-0.24

åŃĺ

-0.23

 sÃ¼r

-0.23

asonry

-0.23

UIT

-0.23

POSITIVE LOGITS

å¼Ģå°ģ

0.28

å¤§å®¶

0.26

Mat

0.25

patibility

0.25

><![

0.25

PCS

0.24

 mater

0.24

ply

0.24

SCRIBE

0.23

mat

0.23

Activations Density 0.002%

article

No Comments

No Known Activations