INDEX

Explanations

geographical regions/names

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gon

-0.35

gia

-0.29

 strips

-0.28

ITT

-0.28

agit

-0.27

strip

-0.26

åıĳå¸ĥæĹ¶éĹ´

-0.26

åįĥäº¿

-0.25

joining

-0.25

itt

-0.25

POSITIVE LOGITS

å¯Ĥå¯ŀ

0.31

 Actors

0.30

éĢĹ

0.30

ucha

0.26

 Actor

0.26

estring

0.25

Actor

0.25

ecer

0.24

çĭ¬ç«ĭ

0.24

 actor

0.24

Activations Density 0.042%

geographical regions/names

No Comments

No Known Activations