INDEX

Explanations

Little

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

fre

-0.24

_DP

-0.24

aises

-0.23

ãĥ¼ãĤ¿ãĥ¼

-0.23

WithContext

-0.23

eters

-0.22

 exam

-0.22

culate

-0.22

 exposition

-0.21

åģģ

-0.21

POSITIVE LOGITS

æĭ³å¤´

0.25

IDL

0.25

 Strategy

0.25

Äĥr

0.24

æĢ§è´¨

0.24

icast

0.24

èĦĨ

0.24

à¸Ĺà¸³à¹Ħà¸¡

0.23

çł´è£Ĥ

0.23

é¡½

0.23

Activations Density 0.051%

Little

No Comments

No Known Activations