INDEX

Explanations

Names

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

èī¯æĢ§

-0.27

gre

-0.25

 ÑĩÐ°

-0.25

alyzer

-0.25

 forms

-0.25

Advertisements

-0.24

undi

-0.24

æŁ¥

-0.24

br

-0.24

mut

-0.23

POSITIVE LOGITS

ean

0.29

è½´

0.29

è´»

0.26

-ca

0.24

æ»ĳ

0.24

arend

0.23

ä¹Ŀåįģ

0.23

ä¿ĿæĬ¤

0.23

DER

0.23

MAY

0.23

Activations Density 0.002%

Names

No Comments

No Known Activations