INDEX

Explanations

Politics, locations, travel

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

lah

-0.28

 ConsoleColor

-0.28

éĢ£

-0.27

 corner

-0.26

æ¯«ä¸į

-0.25

;',

-0.25

ulin

-0.25

 cola

-0.24

`'

-0.24

åīµ

-0.24

POSITIVE LOGITS

ä¸īä»£

0.29

åħ³åı£

0.28

åĨįéĢł

0.27

åĨįè¯´

0.27

atÃ³

0.26

UBE

0.25

 projects

0.24

 automÃ¡t

0.24

hod

0.24

omore

0.23

Activations Density 0.007%

Politics, locations, travel

No Comments

No Known Activations