INDEX

Explanations

Code, jargon, and random words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cho

-0.27

strand

-0.25

UEL

-0.25

æĬĺ

-0.25

reb

-0.25

clid

-0.25

 Prospect

-0.24

ueva

-0.23

RB

-0.23

wick

-0.23

POSITIVE LOGITS

gst

0.29

FormatException

0.28

ç½©

0.28

apult

0.27

Ĩµ

0.27

edb

0.26

olatile

0.26

äººæ°Ķ

0.25

azers

0.25

å±ı

0.24

Activations Density 0.020%

Code, jargon, and random words

No Comments

No Known Activations