INDEX

Explanations

descent

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 uncovered

-0.28

esa

-0.28

 works

-0.26

 minim

-0.25

DIE

-0.25

contr

-0.25

ç´

-0.25

ur

-0.25

 refin

-0.24

 contr

-0.24

POSITIVE LOGITS

_Blue

0.29

çĲĨäºĭéķ¿

0.29

éģĵ

0.28

 Caucus

0.27

ÐºÑĢÐ°

0.27

posÃ©

0.27

ormap

0.26

REAK

0.25

IME

0.25

quez

0.25

Activations Density 0.036%

descent

No Comments

No Known Activations