INDEX

Explanations

various document sections

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

Com

-0.26

itt

-0.25

pherd

-0.24

itte

-0.24

KeyType

-0.24

vements

-0.24

æĺ±

-0.24

ette

-0.24

ITT

-0.24

feit

-0.23

POSITIVE LOGITS

æ³ķäºº

0.32

æ¥¼

0.26

SAX

0.26

aversable

0.25

ellers

0.25

åĢ¾

0.24

çĪµ

0.24

èĲ¥

0.24

ta

0.23

_reporting

0.23

Activations Density 0.001%

various document sections

No Comments

No Known Activations