INDEX

Explanations

Improvement

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rite

-0.29

onium

-0.29

 setC

-0.28

èĥ½åģļåĪ°

-0.28

ç¦ĭ

-0.26

åĨĻçļĦ

-0.25

çĽ¸äº²

-0.25

é£İæĻ¯åĮº

-0.25

-tone

-0.25

TU

-0.25

POSITIVE LOGITS

its

0.28

åıĹ

0.27

ades

0.27

 prompting

0.25

Eph

0.25

æİĪ

0.25

æĮĩæĮ¥

0.24

è¯Ŀ

0.24

its

0.24

okie

0.24

Activations Density 0.000%

Improvement

No Comments

No Known Activations