INDEX

Explanations

code fragments

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

SDL

-0.28

SDL

-0.26

bom

-0.25

swe

-0.25

Bird

-0.25

SDL

-0.25

æ¹ĵ

-0.25

vie

-0.24

riers

-0.24

(Parcel

-0.24

POSITIVE LOGITS

éĤĳ

0.31

 trÃł

0.29

çŃ¾

0.27

çĥŃåº¦

0.27

iagnostics

0.27

è´Ł

0.26

åĩĮ

0.25

imas

0.25

wit

0.25

ç®ķ

0.25

Activations Density 0.010%

code fragments

No Comments

No Known Activations