INDEX

Explanations

document snippets

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

eni

-0.30

ske

-0.29

eno

-0.28

ÅĤe

-0.27

ãģĭãģĳãģ¦

-0.26

iza

-0.25

áº¿p

-0.25

ican

-0.24

å¯Ĳ

-0.24

 douche

-0.23

POSITIVE LOGITS

alf

0.27

 Classic

0.26

FormData

0.26

Configurer

0.25

å®ŀè·µç»ıéªĮ

0.24

ichel

0.24

 Vaugh

0.23

(*)

0.23

peating

0.23

RACT

0.23

Activations Density 0.002%

document snippets

No Comments

No Known Activations