INDEX

Explanations

documents and organizations

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

 Conserv

-0.29

Ð»Ð¾Ð¶Ð¸ÑĤÑĮ

-0.28

å®ļåĲĳ

-0.28

ivable

-0.27

çĪ±å¥½

-0.27

 newNode

-0.25

orthy

-0.25

ĥĿ

-0.25

rego

-0.25

åĨįçİ°

-0.24

POSITIVE LOGITS

åĢŁæŃ¤

0.28

å¥Ĺ

0.27

ÕŃ

0.26

":

0.26

 asserting

0.26

 userList

0.26

 Swan

0.25

åĴİ

0.25

 stating

0.25

ufig

0.24

Activations Density 0.002%

documents and organizations

No Comments

No Known Activations