INDEX

Explanations

intelligence

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

åĶ¯

-0.26

doc

-0.26

eko

-0.25

erno

-0.25

dart

-0.25

emb

-0.25

ollections

-0.25

makt

-0.24

æĥ³æī¾

-0.24

 Established

-0.24

POSITIVE LOGITS

 minds

0.26

 mind

0.24

reno

0.24

æ§Į

0.24

itate

0.24

hum

0.24

geh

0.24

 humane

0.23

æĽ´æľī

0.23

 rebel

0.23

Activations Density 7.320%

intelligence

No Comments

No Known Activations