INDEX

Explanations

result

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

 sadd

-0.27

 tack

-0.26

æĭįæĭį

-0.25

 marketer

-0.24

 punch

-0.24

 lining

-0.24

arlo

-0.24

_neighbors

-0.24

éĤ»

-0.24

Audit

-0.24

POSITIVE LOGITS

deen

0.32

illes

0.30

LES

0.28

ILLE

0.27

æ¯Ķè¾ĥ

0.26

ille

0.26

åħĨ

0.26

æ²³æµģåŁŁ

0.25

lost

0.25

 Bradford

0.25

Activations Density 0.002%

result

No Comments

No Known Activations