INDEX

Explanations

insects and ticks

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

berries

-0.26

eguard

-0.26

á»Ļt

-0.26

éĦĤ

-0.25

oter

-0.25

 kÃ¼Ã§

-0.25

åĪĩ

-0.25

æĪĲé¾Ļ

-0.24

atrix

-0.24

roach

-0.24

POSITIVE LOGITS

å¤¹

0.37

å¤

0.28

gr

0.27

zl

0.27

zik

0.27

 sulf

0.27

Dir

0.26

å·´æĸ¯

0.26

gr

0.26

sin

0.26

Activations Density 0.001%

insects and ticks

No Comments

No Known Activations