INDEX

Explanations

comparisons, examples

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

($.

-0.27

ocrine

-0.26

UR

-0.26

éª¨å¤´

-0.25

imenti

-0.25

 BrowserAnimationsModule

-0.24

intl

-0.24

 pick

-0.24

UR

-0.23

éħ±

-0.23

POSITIVE LOGITS

ç²Ĺç³Ļ

0.29

ç²Ĺ

0.25

ras

0.25

ĥĿ

0.24

epad

0.24

Nor

0.24

ä¸įåĩºæĿ¥

0.23

çĥ«

0.23

Ĳľç´¢

0.23

altung

0.23

Activations Density 0.000%

comparisons, examples

No Comments

No Known Activations