INDEX

Explanations

half

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_INCLUDED

-0.27

isphere

-0.25

EAR

-0.25

åģļäºĭ

-0.24

Opp

-0.24

fav

-0.24

 labs

-0.24

(names

-0.23

æĬĺ

-0.23

ÅĤam

-0.23

POSITIVE LOGITS

ammen

0.26

isten

0.26

Wah

0.25

ancell

0.24

 expressing

0.24

 defendant

0.23

 desn

0.23

upiter

0.23

èī²

0.23

_residual

0.23

Activations Density 0.001%

half

No Comments

No Known Activations