INDEX

Explanations

code

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

uga

-0.27

å¦Ĩ

-0.27

ç§¯ç´¯

-0.26

benh

-0.25

iances

-0.25

çľŁ

-0.25

å²ģ

-0.24

é¾Ł

-0.23

iate

-0.23

nels

-0.23

POSITIVE LOGITS

æĢİä¹Īçľĭ

0.26

Cas

0.25

åŃĹç¬¬

0.24

Unnamed

0.24

NotExist

0.24

å®Įåħ¨ä¸įåĲĮ

0.24

 sollen

0.23

Xd

0.23

 camer

0.23

æľīå¾Īå¤ļç§į

0.23

Activations Density 7.354%

code

No Comments

No Known Activations