INDEX

Explanations

American

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

Che

-0.28

áº¡m

-0.28

Che

-0.26

itter

-0.25

che

-0.25

aces

-0.24

 ØªØ¹

-0.24

 authors

-0.24

æĮ½

-0.24

ens

-0.24

POSITIVE LOGITS

å°ģ

0.31

leground

0.28

imenti

0.26

 Wizard

0.25

ç©°

0.25

æĦİ

0.25

à¹Ģà¸Ħà¸£à¸Ķ

0.24

owards

0.23

 trump

0.23

 Suff

0.23

Activations Density 0.001%

American

No Comments

No Known Activations