INDEX

Explanations

non-english characters/code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oting

-0.26

æĪ·

-0.26

å¼¥è¡¥

-0.26

çĺ¸

-0.26

 Frames

-0.25

uges

-0.25

owell

-0.24

avs

-0.24

ierz

-0.24

 limitation

-0.24

POSITIVE LOGITS

ForKey

0.28

å½¹

0.28

 litt

0.26

ìĹŃ

0.26

erule

0.25

 nich

0.25

ITT

0.24

earch

0.24

 quiet

0.24

offs

0.24

Activations Density 0.001%

non-english characters/code

No Comments

No Known Activations