INDEX

Explanations

vacancy

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

lash

-0.31

gang

-0.29

è¿ľæĸ¹

-0.28

éĥħ

-0.28

 drained

-0.27

 stain

-0.27

usta

-0.26

.Typed

-0.25

%%%

-0.25

æĤ¬

-0.25

POSITIVE LOGITS

rypt

0.25

éº¸

0.25

ivel

0.25

èĬ³

0.25

-des

0.24

 Admir

0.24

 Carm

0.23

emaker

0.23

ik

0.23

Ã¤ch

0.23

Activations Density 0.206%

vacancy

No Comments

No Known Activations